A New Model for International, Privacy-Preserving Data Science
summary
A phase‑one pilot demonstrates a remote, privacy‑preserving workflow that uses PySyft with nodes hosted at NSOs and a network gateway at the UN PET Lab to run a private join on synthetic UN Comtrade data. Python queries travel to domain servers via an ambassador for code review, run on each NSO’s private data, and return reviewed results without exposing raw records. The system works for mock data; real private runs are future work.
AI-written summary · about
chapters (7)
- 0:00Census Bureau’s project intro
- 1:48International data collaboration
- 4:17Introducing PLEES on XD
- 6:04PFT platform privacy
- 7:30Traditional vs new privacy
- 8:12Project state and future
- 9:38Next steps and expansion
related talks
14mEstablishing Privacy Metrics for Genomic Data Analysis
16mPrivacy in the Public Sector: Lessons Learned and Strategies for Success
50mPrivacy in Practice with Smart Pseudonymization: Lessons from the Belgian Public Sector
01h 19mWhen Data Can’t Move but Insight Must
30mSharing without Sharing: the Case for Data Clean Rooms Powered by Confidential Computing
46mPrivacy Preserving IoT
28mPrivacy Engineering Networking Break AMA
54mOpening Keynote